New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Mas Module Boundary

by AUTO-MAS-Project in AUTO-MAS-Project/AUTO-MAS

Define and enforce backend module boundaries for Python services.

AGPL-3.0Auto-check passedDevelopment

Install Mas Module Boundary

skills CLI
$ npx skills add AUTO-MAS-Project/AUTO-MAS --skill mas-module-boundary -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AUTO-MAS-Project/AUTO-MAS mas-module-boundary --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AUTO-MAS-Project/AUTO-MAS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/mas-module-boundary .claude/skills/mas-module-boundary && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mas-module-boundary
GitHub stars
710
Token cost
~1.6k tokens
SKILL.md length
812 words
Files
2
Skills in repo
15
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Define and enforce backend module boundaries for Python services.

  • Works in 6 steps: models/schema: external API contract and… → api: request parsing, response shaping,… → core: orchestration, lifecycle, task… → …
  • Refactoring backend code under app/
  • SKILL.md covers Objective, Layer Model, Current Dev Map and Dependency Direction, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Mas Module Boundary is an agent skill from AUTO-MAS-Project/AUTO-MAS. Define and enforce backend module boundaries for Python services. Use when adding or refactoring backend code under app/, reviewing dependency direction, deciding layer ownership, or preventing logic leakage across schema/api/core/services/task/utils modules.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Refactoring. It works with Python. The repository describes itself as: 多脚本多配置统一管理与自动化工具 | 轻松管理大量脚本并存储多个用户配置、设计自动化任务流、监看脚本日志，大幅提高自动化代理效率与稳定性！. The licence is AGPL-3.0.

When your agent uses it

  • Refactoring backend code under app/
  • Reviewing dependency direction
  • Deciding layer ownership
  • Preventing logic leakage across schema/api/core/services/task/utils modules

Example prompts

  • “/mas-module-boundary”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. models/schema: external API contract and typed data structure.
  2. api: request parsing, response shaping, transport concerns.
  3. core: orchestration, lifecycle, task scheduling, state coordination.
  4. task: script-domain execution flow.
  5. services: system/network/integration capabilities.
  6. utils: reusable low-level helpers with no business policy.

What it can do on your machine

Read from SKILL.md and the folder at commit 699de5a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mas Module Boundary loads about 1.6k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 812 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AUTO-MAS-Project/AUTO-MAS at commit 699de5a, republished under its AGPL-3.0 licence (© AUTO-MAS-Project). 812 words, ~1,650 tokens.

Download SKILL.mdSave it as .claude/skills/mas-module-boundary/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
mas-module-boundary
description
Define and enforce backend module boundaries for Python services. Use when adding or refactoring backend code under app/, reviewing dependency direction, deciding layer ownership, or preventing logic leakage across schema/api/core/services/task/utils modules.

MAS Module Boundary

Objective

Keep backend code maintainable by enforcing clear ownership, dependency direction, and placement rules across modules.

Layer Model

  1. models/schema: external API contract and typed data structure.
  2. api: request parsing, response shaping, transport concerns.
  3. core: orchestration, lifecycle, task scheduling, state coordination.
  4. task: script-domain execution flow.
  5. services: system/network/integration capabilities.
  6. utils: reusable low-level helpers with no business policy.

Current Dev Map

  1. API routes: app/api/*.py
  2. Runtime orchestration: app/core/*.py
  3. Schema/config/runtime models: app/models/schema.py, app/models/config.py, app/models/task.py, app/models/ConfigBase.py
  4. Script domains: app/task/MAA, app/task/general, app/task/SRC

Dependency Direction

  1. api -> core/services/models.schema
  2. core -> services/task/models/utils
  3. task -> core/services/models/utils
  4. services -> utils/models
  5. models -> none of api/core/services/task

Disallowed examples:

  1. models/schema importing core or services
  2. utils importing core or api
  3. services importing concrete api routers
  4. api embedding long-running workflow loops directly

Ownership Rules

  1. app/models/schema.py: naming, typing, field descriptions only. No filesystem, network, process, or business branching.
  2. app/api/*: accept *In, return *Out/OutBase, validate input, call core/services, shape response.
  3. app/core/*: own global coordination, lifecycle, config composition, task scheduling, and broadcast.
  4. app/task/*: own per-script execution lifecycle (check/prepare/run/final) and domain task decisions.
  5. app/services/*: wrap external integrations and provide stable capabilities to core/task.
  6. app/utils/*: generic helpers and low-level adapters only. No domain policy and no orchestrator imports.
  7. Script-config import/restore policy belongs to core/task orchestration, not api or schema: AUTO-MAS manages other scripts by swapping their config files/folders before and after task execution.
  8. Script success/failure heuristics based on log text, log timestamp, and process exit belong to orchestrators and log-monitor helpers, not to schema models or transport handlers.

Placement Decision Tree

  1. Request/response contract or DTO typing -> models/schema
  2. Endpoint parsing and response mapping -> api
  3. Cross-task orchestration or global runtime state -> core
  4. Script-domain run logic -> task/<domain>
  5. OS/network/third-party integration -> services
  6. Reusable, context-agnostic helper -> utils

Cross-Cutting Rules

  1. Avoid circular imports; if seen, extract interface/helper to a lower layer.
  2. Avoid direct config file IO in api; use a core facade.
  3. Keep business constants close to the owning domain layer.
  4. Shared schema semantics should align with mas-schema-naming.
  5. New config modes or raw-config capabilities must be end-to-end complete: model field, edit entry, persistence path, and runtime consumer must all exist before the feature is considered real.
  6. Do not leave placeholder config fields, fake detailed-mode branches, or dead save paths in one layer when no owning runtime path exists.
  7. Do not create standalone builder, loader, or helper-service modules for a feature that has no second call site and no real ownership boundary.
  8. If a domain can be expressed as one task class plus nearby local helpers, prefer that over creating a mini-subsystem inside the domain folder.
  9. When adding support for a new external script, preserve the product's config-copy plus log-monitor architecture instead of embedding script-specific state machines into shared layers.
  10. Script-specific adaptation is cross-layer by design: add the script config/user config in app/models/config.py, expose schema types in app/models/schema.py, add endpoints in app/api/scripts.py, extend global config orchestration in app/core/config.py, and add task dispatch in app/core/task_manager.py. app/api/scripts.py holds endpoints only: parse the request, call a function exposed by the owning app/task/<Xxx>/ module, shape the response model. Directory handling, import, update, validation, and group propagation belong in the script domain; do not define script-private helpers in the API layer. The MaaFW engine under app/task/MaaFW/ is the exception: its tools/core/ packages must stay host-agnostic and its worker subprocess must not import host modules — see app/task/MaaFW/AGENTS.md before touching it.
  11. For a new script domain, start from the closest existing task folder shape, commonly app/task/general, then rename and adapt domain-specific config, run, manual-review, and manager code in place.
Show full SKILL.md (206 more words)Show less

Anti-Patterns

  1. Business rules inside schema definitions.
  2. Route handlers containing workflow loops or retry engines.
  3. Utility modules importing orchestrators for convenience.
  4. Duplicated policy checks spread across api/core/task without an owner.
  5. A new domain folder that introduces multiple thin modules without actual reuse or boundary pressure.
  6. Route handlers or module-private helpers in app/api/ that carry script-specific business (directory layout, import/update flows, config migration) instead of calling the owning app/task/<Xxx>/ module.

PR Boundary Checklist

  1. Each changed file belongs to the right layer by responsibility.
  2. New imports follow allowed dependency direction.
  3. No new circular dependency is introduced.
  4. Schema changes do not add business execution logic.
  5. API changes keep the thin-controller pattern.
  6. Core/task/services boundaries remain explicit and testable.
  7. New configuration concepts are complete across model, UI, and runtime, or they are not introduced yet.
  8. New helper modules justify their existence with reuse or a real dependency boundary, not just naming neatness.
  9. New script support is complete across config templates, schema, API, task manager dispatch, task folder, and frontend entry points before it is treated as implemented.
  10. Searches for the source template domain, such as GeneralConfig/GeneralUserConfig, were used to find all required registry and branch updates.

© AUTO-MAS-Project, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/mas-module-boundary of AUTO-MAS-Project/AUTO-MAS.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 699de5a

Compare with similar skills

Mas Module Boundary next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Mas Module Boundary compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mas Module Boundary this skillAUTO-MAS-Project/AUTO-MAS710—~1.6kAutomated safety check: PassAGPL-3.0
Dignified Python Standardsdocling-project/docling69k—~1.5kAutomated safety check: PassApache-2.0
Readable Pycrazyguitar/pysheeet8.2k—~2.4kAutomated safety check: PassMIT
Refactor OpCVCUDA/CV-CUDA2.7k—~1.5kAutomated safety check: PassCustom licence
Readable Verilog GeneratorEriemon/verilog-generator312—~5.4kAutomated safety check: PassApache-2.0
Python Designmindfold-ai/Trellis15k—~4kAutomated safety check: PassAGPL-3.0

Similar skills

  • Dignified Python Standards

    docling-project/docling

    Applies opinionated production Python conventions chosen by the project's Python version: modern type syntax, pathlib, explicit checks and interface guidance.

    69k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed

  • Readable Py

    crazyguitar/pysheeet

    Readable Python code rules inspired by The Art of Readable Code.

    8.2k GitHub stars~2.4k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Refactor Op

    CVCUDA/CV-CUDA

    Find and safely apply per-operator refactoring / redundancy-reduction opportunities in a CV-CUDA operator (near-duplicate Tensor/VarShape kernels, reinvented shared utilities, dead code).

    2.7k GitHub stars~1.5k tokensUpdated 22 days ago
    DevelopmentAuto-check passed

  • Readable Verilog Generator

    Eriemon/verilog-generator

    A skill your agent uses when creating, writing, reviewing, annotating, repairing, refactoring, or validating readable Verilog RTL, including synthesizable Verilog-2001 .v files, existing-RTL…

    312 GitHub stars~5.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Python Design

    mindfold-ai/Trellis

    Python design patterns for CLI scripts and utilities — type-first development, deep modules, complexity management, and red flags.

    15k GitHub stars~4k tokensUpdated 10 days ago
    DevelopmentAuto-check passed

  • Nexus Mapper

    Haaaiawd/Nexus-skills

    Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots.

    166 GitHub stars~2.5k tokensUpdated 6 mo ago
    DevelopmentAuto-check: notes

More from AUTO-MAS-Project/AUTO-MAS

All 15 skills in this repo

  • Mas Game Sign

    AUTO-MAS-Project/AUTO-MAS

    Add, refactor, or review AUTO-MAS game community sign-in (game sign) code, including the provider registry in app/tools/gamesign.py, platform adapters for Skland/Miyoushe/Kuro/Taygedo, credential…

    710 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Mas Schema Naming

    AUTO-MAS-Project/AUTO-MAS

    Define canonical naming for future backend schema domains. An agent skill from AUTO-MAS-Project/AUTO-MAS.

    710 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Mas Code Standards

    AUTO-MAS-Project/AUTO-MAS

    A skill your agent uses when implementing, fixing, refactoring, or reviewing non-generated AUTO-MAS code, or when preparing code-style guidance, comments, docstrings, version notes, or Conventional…

    710 GitHub stars~2.5k tokensUpdated today
    Auto-check passed

  • Mas Frontend UI

    AUTO-MAS-Project/AUTO-MAS

    A skill your agent uses when working on AUTO-MAS frontend UI, Ant Design Vue components, page layout, forms, tables, modals, drawers, feedback, empty/loading/error states, drag interactions, dark…

    710 GitHub stars~3.8k tokensUpdated today
    Auto-check passed

  • Mas Script Specialized Adapter

    AUTO-MAS-Project/AUTO-MAS

    Review, add, or refactor AUTO-MAS specialized script adapters by upstream architecture, including MAA, SRC, MaaEnd/MXU, General, ok-script adapters such as Okww and OkNte, multi-engine adapters such…

    710 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Mas API Contract

    AUTO-MAS-Project/AUTO-MAS

    Define backend API contract standards for FastAPI services. An agent skill from AUTO-MAS-Project/AUTO-MAS.

    710 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Mas Module Boundary

What does Mas Module Boundary do?

Define and enforce backend module boundaries for Python services. Mas Module Boundary is an agent skill from AUTO-MAS-Project/AUTO-MAS. Define and enforce backend module boundaries for Python services.

When should I use Mas Module Boundary?

Mas Module Boundary fits situations like: refactoring backend code under app/; reviewing dependency direction; deciding layer ownership; preventing logic leakage across schema/api/core/services/task/utils modules.

How do I install Mas Module Boundary in Claude Code?

Run `npx skills add AUTO-MAS-Project/AUTO-MAS --skill mas-module-boundary -a claude-code`. Or copy the skill folder (.agents/skills/mas-module-boundary in AUTO-MAS-Project/AUTO-MAS) into .claude/skills/mas-module-boundary in your project. Claude Code loads it when a task matches its description.

How do I install Mas Module Boundary in Codex?

Run `npx skills add AUTO-MAS-Project/AUTO-MAS --skill mas-module-boundary -a codex`. Or copy the skill folder (.agents/skills/mas-module-boundary in AUTO-MAS-Project/AUTO-MAS) into .agents/skills/mas-module-boundary in your project. Codex loads it when a task matches its description.

Can I use Mas Module Boundary in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AUTO-MAS-Project/AUTO-MAS --skill mas-module-boundary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mas-module-boundary, .gemini/skills/mas-module-boundary, .github/skills/mas-module-boundary and .opencode/skills/mas-module-boundary in your project.

What does Mas Module Boundary need to run?

SKILL.md names no scripts, command-line tools or credentials: Mas Module Boundary is instructions for the agent only. Our summary lists: Python 3.

Does Mas Module Boundary access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Mas Module Boundary safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Mas Module Boundary use?

Mas Module Boundary is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mas Module Boundary use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mas Module Boundary?

Skills that share tags, products or a category with Mas Module Boundary: Dignified Python Standards (docling-project/docling, 69k stars), Readable Py (crazyguitar/pysheeet, 8.2k stars), Refactor Op (CVCUDA/CV-CUDA, 2.7k stars) and Readable Verilog Generator (Eriemon/verilog-generator, 312 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mas Module Boundary?

AUTO-MAS-Project (a GitHub organization) maintains it in AUTO-MAS-Project/AUTO-MAS, which has 710 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

Source: AUTO-MAS-Project/AUTO-MAS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.